Text processing (level 2)

One interesting application of Python is to use it for analyzing texts written by humans. Written texts are subject to various implicit and explicit rules, such as spelling and grammar. Python can be used to make sense of texts at various levels. For example, we may calculate simple statistics about the length of a document or its parts. Or we may dig a little deeper by analyzing word use, or finding misspelled words or grammar problems. And using big data techniques, we might make an educated guess about the meaning of a piece of writing, or even the attitude that a text represents.

Day 1: Text statistics

Day 2: Text cleanup

Day 3: Sentiment analysis

  • Learn how to read text from files in Python.

  • Assignment Perform a sentiment analysis on a large text fragment.

  • Assignment Present an overview of the sentiment contained in a collection of tweets.


When you’re ready to submit, head to the submit page for this module.

When you’ve finished

You might take a look at these resources for further study: